Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 4676 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.9276. Min Act: -0.0000
Data Index: 1045392 (The Pile)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.9170. Min Act: 0.0000
Data Index: 481842 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.8965. Min Act: -0.0000
Data Index: 1957902 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.6907. Min Act: -0.0000
Data Index: 655306 (The Pile)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.5278. Min Act: 0.0002
Data Index: 871261 (The Pile)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.6198. Min Act: -0.0000
Data Index: 1922108 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.5180. Min Act: -0.0000
Data Index: 1236750 (The Pile)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.5726. Min Act: 0.0000
Data Index: 548984 (The Pile)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.5583. Min Act: 0.0001
Data Index: 1174778 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.6208. Min Act: 0.0000
Data Index: 228565 (The Pile)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.5312. Min Act: -0.0000
Data Index: 976931 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.4645. Min Act: 0.0000
Data Index: 477078 (The Pile)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.4478. Min Act: 0.0000
Data Index: 1230039 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.4253. Min Act: -0.0000
Data Index: 831045 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.4075. Min Act: 0.0000
Data Index: 1961309 (The Pile)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.3684. Min Act: -0.0000
Data Index: 780018 (The Pile)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.2862. Min Act: -0.0000
Data Index: 645988 (The Pile)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.3361. Min Act: -0.0000
Data Index: 1911215 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.2459. Min Act: -0.0000
Data Index: 440881 (The Pile)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9276. Min Range: -1.9276
Max Act: 1.3157. Min Act: -0.0000
Data Index: 376877 (The Pile)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19